Geodesic
A simplex trained neural network-based architecture for sensor fusion and tracking of target maneuvers
Kybernetika, Tome 35 (1999) no. 5, pp. 613-636 Cet article a éte moissonné depuis la source Czech Digital Mathematics Library

Voir la notice de l'article

One of the major applications for which neural network-based methods are being successfully employed is in the design of intelligent integrated processing architectures that efficiently implement sensor fusion operations. In this paper we shall present a novel scheme for developing fused decisions for surveillance and tracking in typical multi-sensor environments characterized by the disparity in the data streams arriving from various sensors. This scheme employs an integration of a multilayer neural network trained with features extracted from the multi-sensor data and a Kalman filter in order to permit reliable tracking of maneuvering targets, and provides an intelligent way of implementing an overa without any attendant increases in computational complexity. A particular focus is given to optimizing the neural network architecture and the learning strategy which are particularly critical to develop the capabilities required for tracking of target maneuvers. Towards these goals, a network growing scheme and a simplex algorithm that seeks the global minimum of the training error are presented. To provide validation of these methods, results of several tracking experiments involving targets executing complex maneuvers in noisy and clutter environments are presented.
One of the major applications for which neural network-based methods are being successfully employed is in the design of intelligent integrated processing architectures that efficiently implement sensor fusion operations. In this paper we shall present a novel scheme for developing fused decisions for surveillance and tracking in typical multi-sensor environments characterized by the disparity in the data streams arriving from various sensors. This scheme employs an integration of a multilayer neural network trained with features extracted from the multi-sensor data and a Kalman filter in order to permit reliable tracking of maneuvering targets, and provides an intelligent way of implementing an overa without any attendant increases in computational complexity. A particular focus is given to optimizing the neural network architecture and the learning strategy which are particularly critical to develop the capabilities required for tracking of target maneuvers. Towards these goals, a network growing scheme and a simplex algorithm that seeks the global minimum of the training error are presented. To provide validation of these methods, results of several tracking experiments involving targets executing complex maneuvers in noisy and clutter environments are presented.
Classification : 68M10, 90B06, 90B40, 92B20, 93E11
Keywords: neural network; multi-sensor environment; simplex algorithm; sensor fusion operations; Kalman filter 
@article{KYB_1999_35_5_a4,
     author = {Wong, Yee Chin and Sundareshan, Malur K.},
     title = {A simplex trained neural network-based architecture for sensor fusion and tracking of target maneuvers},
     journal = {Kybernetika},
     pages = {613--636},
     year = {1999},
     volume = {35},
     number = {5},
     mrnumber = {1728471},
     zbl = {1274.93265},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/KYB_1999_35_5_a4/}
}
TY  - JOUR
AU  - Wong, Yee Chin
AU  - Sundareshan, Malur K.
TI  - A simplex trained neural network-based architecture for sensor fusion and tracking of target maneuvers
JO  - Kybernetika
PY  - 1999
SP  - 613
EP  - 636
VL  - 35
IS  - 5
UR  - http://geodesic.mathdoc.fr/item/KYB_1999_35_5_a4/
LA  - en
ID  - KYB_1999_35_5_a4
ER  - 
%0 Journal Article
%A Wong, Yee Chin
%A Sundareshan, Malur K.
%T A simplex trained neural network-based architecture for sensor fusion and tracking of target maneuvers
%J Kybernetika
%D 1999
%P 613-636
%V 35
%N 5
%U http://geodesic.mathdoc.fr/item/KYB_1999_35_5_a4/
%G en
%F KYB_1999_35_5_a4
Wong, Yee Chin; Sundareshan, Malur K. A simplex trained neural network-based architecture for sensor fusion and tracking of target maneuvers. Kybernetika, Tome 35 (1999) no. 5, pp. 613-636. http://geodesic.mathdoc.fr/item/KYB_1999_35_5_a4/

[2] Bar–Shalom Y., Li X. R.: Estimation and Tracking. Artech House, 1993 | MR | Zbl

[3] Bogler P. L.: Tracking a maneuvering target using input estimation. IEEE Trans. Aerospace Electron. Systems AES-23 (1987), 298–310 | DOI

[4] Box G. E. P., Jenkins G. M.: Time Series Analysis, Forecasting and Control. Holden Day, San Francisco 1970 | MR | Zbl

[5] Chan Y. T., Hu A., Plant J. B.: A Kalman filter based tracking scheme with input estimation. IEEE Trans. Aerospace Electron. Systems (1979), 237–244

[9] Hagan M. T., Demuth H. B., Beale M.: Neural Network Desig.

[14] Nelder A. J., Mead R.: A simplex method for function minimizatio.

[18] Sworder D. D.: Image enhanced tracking. IEEE Trans. Aerospace Electron. Systems AES-25 (1989), 701–710 | DOI